© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24132
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensburg
    -0.09
    ahre
    -0.08
    jec
    -0.07
    ấp
    -0.07
    å°ıåı·
    -0.07
    ÅŁt
    -0.07
    .bz
    -0.06
    æĭĽè´¢
    -0.06
    theless
    -0.06
    ÅŁte
    -0.06
    POSITIVE LOGITS
    /generated
    0.07
    åĩĨå¤ĩçļĦ
    0.07
    说ä¸įåĩº
    0.07
    è£Ķ
    0.06
    illon
    0.06
    pollo
    0.06
    iago
    0.06
    odore
    0.06
    asakan
    0.06
    éĩį大çļĦ
    0.06
    Activations Density 0.000%

    No Known Activations